public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Williams <peterw@aurema.com>
To: Peter Chubb <peter@chubb.wattle.id.au>
Cc: Paul Jackson <pj@sgi.com>, Joachim B Haga <c.j.b.haga@fys.uio.no>,
	miller@techsource.com, linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH] O(1) Entitlement Based Scheduler
Date: Tue, 02 Mar 2004 12:25:52 +1100	[thread overview]
Message-ID: <4043E2A0.9000107@aurema.com> (raw)
In-Reply-To: <16450.32046.538912.553878@wombat.chubb.wattle.id.au>

Peter Chubb wrote:
>>>>>>"Paul" == Paul Jackson <pj@sgi.com> writes:
> 
> 
> 
> Paul> Is there anyway to provide a mechanism that would support
> Paul> administering a system as follows:
> 
> Paul>   1) Users get so much CPU usage allowed, determined by an upper
> Paul> limit on a running average of the combined CPU usage of all
> Paul> their tasks, with a half life perhaps on the order of minutes.
> 
> Paul>   2) They can nice their tasks up and down, within a decent
> Paul> range, as they will.
> 
> Paul>   3) But if they push too close to their allowed limit, all
> Paul> their tasks get reined in.  The relative priorities within their
> Paul> own tasks are not changed, but the priority of their tasks
> Paul> relative to other users is weakened.
> 
> This is exactly what the commercial product ARMtech does.  The EBS
> that Aurema have just released as open source is (a small) part of the
> commercial product.

Not strictly speaking a part of our commercial product but based on the 
CPU scheduling technology in that product.  As you know, the CPU 
scheduler in the kernel based versions of our product relies on a 
generic "plug in scheduler" interface being present in the host kernel 
and runtime loadable kernel modules plug into that interface and take 
over scheduling.  This mechanism (while allowing our product to work on 
a number of different host operating systems) has the disadvantage that 
it adds some overhead to the scheduler (this is in addition to the extra 
overhead involved in hierarchical scheduling) and places some 
restrictions on the scheduler design as it cannot make too many 
assumptions about the underlying scheduler in the host operating system.

When the technology is used to build an embedded scheduler (as is the 
case with EBS) significant improvements in efficiency can be realised. 
So EBS is a souped up, non hierarchical version of our CPU scheduler 
designed specially for Linux.

> 
> See http://www.aurema.com
> 
> Peter C (an ex-employee of Aurema)
> 
> --
> Dr Peter Chubb  http://www.gelato.unsw.edu.au  peterc AT gelato.unsw.edu.au
> The technical we do immediately,  the political takes *forever*

Cheers
Peter
-- 
Dr Peter Williams, Chief Scientist                peterw@aurema.com
Aurema Pty Limited                                Tel:+61 2 9698 2322
PO Box 305, Strawberry Hills NSW 2012, Australia  Fax:+61 2 9699 9174
79 Myrtle Street, Chippendale NSW 2008, Australia http://www.aurema.com



  reply	other threads:[~2004-03-02  1:26 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <894006121@toto.iv>
2004-03-01  0:00 ` [RFC][PATCH] O(1) Entitlement Based Scheduler Peter Chubb
2004-03-02  1:25   ` Peter Williams [this message]
     [not found] <1vuMd-5jx-5@gated-at.bofh.it>
     [not found] ` <1vuMd-5jx-7@gated-at.bofh.it>
     [not found]   ` <1vuMd-5jx-9@gated-at.bofh.it>
     [not found]     ` <1vuMd-5jx-11@gated-at.bofh.it>
     [not found]       ` <1vuMd-5jx-3@gated-at.bofh.it>
     [not found]         ` <1vvyx-6jy-13@gated-at.bofh.it>
     [not found]           ` <1vBE2-48V-21@gated-at.bofh.it>
2004-03-03 21:38             ` Bill Davidsen
     [not found] <fa.fi4j08o.17nchps@ifi.uio.no.suse.lists.linux.kernel>
     [not found] ` <fa.ctat17m.8mqa3c@ifi.uio.no.suse.lists.linux.kernel>
     [not found]   ` <yydjishqw10p.fsf@galizur.uio.no.suse.lists.linux.kernel>
     [not found]     ` <40426E1C.8010806@aurema.com.suse.lists.linux.kernel>
2004-03-03  2:48       ` Andi Kleen
2004-03-03  3:45         ` Peter Williams
2004-03-03 10:13           ` Andi Kleen
2004-03-03 23:46             ` Peter Williams
2004-03-03 15:57           ` Andi Kleen
2004-03-04  0:41             ` Peter Williams
2004-03-05  3:55               ` Andi Kleen
     [not found] <fa.ftul5bl.nlk3pr@ifi.uio.no>
     [not found] ` <fa.cvc8vnj.ahebjd@ifi.uio.no>
2004-03-01  9:18   ` Joachim B Haga
2004-03-01 10:18     ` Paul Wagland
2004-03-01 19:11       ` Mike Fedyk
     [not found] <fa.jgj0bdi.b3u6qk@ifi.uio.no>
2004-03-01  1:54 ` Andy Lutomirski
2004-03-01  2:54   ` Peter Williams
2004-03-01  3:46     ` Andy Lutomirski
2004-03-01  4:18       ` Peter Williams
2004-03-02 23:36   ` Peter Williams
     [not found] <fa.fi4j08o.17nchps@ifi.uio.no>
     [not found] ` <fa.ctat17m.8mqa3c@ifi.uio.no>
2004-02-29 11:58   ` Joachim B Haga
2004-02-29 20:39     ` Paul Jackson
2004-02-29 22:56     ` Peter Williams
     [not found] <1t8wp-qF-11@gated-at.bofh.it>
     [not found] ` <1th6J-az-13@gated-at.bofh.it>
     [not found]   ` <403E2929.2080705@tmr.com>
2004-02-27  3:44     ` Rik van Riel
2004-02-28 21:27       ` Bill Davidsen
2004-02-28 23:55         ` Peter Williams
2004-03-04 21:08           ` Timothy Miller
     [not found] <1tfy0-7ly-29@gated-at.bofh.it>
     [not found] ` <1thzJ-A5-13@gated-at.bofh.it>
     [not found]   ` <1tjrN-2m5-1@gated-at.bofh.it>
     [not found]     ` <1tjLa-2Ab-9@gated-at.bofh.it>
     [not found]       ` <1tlaf-3OY-11@gated-at.bofh.it>
     [not found]         ` <1tljX-3Wf-5@gated-at.bofh.it>
     [not found]           ` <1tznd-CP-35@gated-at.bofh.it>
     [not found]             ` <1tzQe-10s-25@gated-at.bofh.it>
2004-02-26 20:14               ` Bill Davidsen
2004-02-26  3:30 Albert Cahalan
2004-02-26  6:19 ` Peter Williams
2004-02-26 17:57   ` Albert Cahalan
2004-02-26 23:24     ` Peter Williams
2004-03-01  3:47       ` Peter Williams
     [not found] <fa.f12rt3d.c0s9rt@ifi.uio.no>
     [not found] ` <fa.ishajoq.q5g90m@ifi.uio.no>
2004-02-25 23:33   ` Junio C Hamano
2004-02-26  8:15     ` Catalin BOIE
  -- strict thread matches above, loose matches on Subject: below --
2004-02-25 14:35 John Lee
2004-02-25 17:09 ` Timothy Miller
2004-02-25 22:12   ` John Lee
2004-02-26  0:31     ` Timothy Miller
2004-02-26  2:04       ` John Lee
2004-02-26  2:18       ` Peter Williams
2004-02-26  2:42         ` Mike Fedyk
2004-02-26  4:10           ` Peter Williams
2004-02-26  4:19             ` Mike Fedyk
2004-02-26 19:23               ` Shailabh Nagar
2004-02-26 19:46                 ` Mike Fedyk
2004-02-26 20:42                   ` Shailabh Nagar
2004-02-26 16:10           ` Timothy Miller
2004-02-26 19:47             ` Mike Fedyk
2004-02-26 22:51             ` Peter Williams
2004-02-27 10:06               ` Helge Hafting
2004-02-27 11:04                 ` Peter Williams
2004-02-26 16:08         ` Timothy Miller
2004-02-26 16:51           ` Rik van Riel
2004-02-26 20:15           ` Peter Williams
2004-02-27 14:46             ` Timothy Miller
2004-02-28  5:00               ` Peter Williams
2004-03-04 21:18         ` Robert White
2004-03-04 23:15           ` Peter Williams
2004-02-26  2:48       ` Nuno Silva
2004-02-26  4:25         ` Peter Williams
2004-02-26 15:57           ` Rik van Riel
2004-02-26 19:28             ` Shailabh Nagar
2004-02-26 16:12         ` Timothy Miller
2004-02-25 22:51 ` Pavel Machek
2004-02-26  3:14   ` John Lee
2004-02-25 23:45 ` Rik van Riel
2004-02-26  7:18 ` John Lee

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4043E2A0.9000107@aurema.com \
    --to=peterw@aurema.com \
    --cc=c.j.b.haga@fys.uio.no \
    --cc=linux-kernel@vger.kernel.org \
    --cc=miller@techsource.com \
    --cc=peter@chubb.wattle.id.au \
    --cc=pj@sgi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox